Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the full load, and it does disclose key behavior: the output is an unsigned transaction (nothing is signed or broadcast), access rules vary by curve version, and the optional wallet adds a preflight covering agent pass, ETH balance, eth_call simulation, problems, and next step. It omits slippage enforcement/defaults and the shape of the returned tx, which are the remaining behavioral gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose in the first clause, then access rules, then the optional preflight — three tight sentences with no filler. The nested parenthetical listing of preflight checks is dense but earns its place by telling the agent what it gets back.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-parameter builder with no annotations, no output schema, and 25% schema coverage, the description covers purpose, versioned access rules, and the preflight option, but leaves the agent guessing about ETH amount units, slippage behavior, and what the unsigned-transaction return actually contains before it can call this confidently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 25% and the description compensates for almost none of it: 'eth' units/format (decimal ETH vs wei), 'token' identifier form (address vs symbol), and 'slippagePct' default/bounds are all unaddressed. The only parameter it touches is 'wallet', where it merely restates the schema's own description of the preflight behavior with no added meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Unsigned tx: buy an AgentPad token on its curve') and the 'unsigned' qualifier separates it from an execution tool in spirit, but it never names the adjacent siblings (quote_buy for pricing, agentpad_buy/onboard_and_buy for signing+submitting), so the buy-side routing is left to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives real preconditions: v2 curves are open to any wallet, v1 curves (e.g. APAD) require a registered agent before graduation — this tells the agent when the call will fail for a given token. It stops short of recommending alternatives (quoting first, or using the higher-level buy tool that signs), so no explicit alternative routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.